Review of Non-Technical Losses Identification Techniques

Illegally consumption of electric power, termed as non-technical losses for the distribution companies is one dominant factors all over world many years. Although there are some conventional methods to identify these irregularities, such physical inspection meters at consumer premises etc, but it requires large number manpower and time; then also does not seem be adequate. Now a days various algorithms have been developed that proposed in different research papers, detect losses. In this paper reviewed, their important features highlighted limitations identified. Finally, qualitative comparison identification presented based on performance, costs, data handling, quality control execution times. It can concluded graph-based classifier, Optimum-Path Forest algorithm both supervised unsupervised variants, yields most accurate result